J1N2/gte-large-en-v1.5-based-ft-prompt-injection-detection-241205Weighted-44

README.md

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Alibaba-NLP/gte-large-en-v1.5
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: gte-large-en-v1.5-based-ft-prompt-injection-detection-241205Weighted-44
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# gte-large-en-v1.5-based-ft-prompt-injection-detection-241205Weighted-44
+
+This model is a fine-tuned version of [Alibaba-NLP/gte-large-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2193
+- F1: 0.9463
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 50
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | F1     |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.4603        | 0.2527 | 100  | 0.2243          | 0.9083 |
+| 0.2014        | 0.5054 | 200  | 0.1719          | 0.9377 |
+| 0.1679        | 0.7581 | 300  | 0.1354          | 0.9486 |
+| 0.1497        | 1.0107 | 400  | 0.1174          | 0.9543 |
+| 0.1062        | 1.2634 | 500  | 0.1451          | 0.9490 |
+| 0.1117        | 1.5161 | 600  | 0.1379          | 0.9504 |
+| 0.1156        | 1.7688 | 700  | 0.1235          | 0.9533 |
+| 0.1155        | 2.0215 | 800  | 0.1305          | 0.9562 |
+| 0.0784        | 2.2742 | 900  | 0.1372          | 0.9530 |
+| 0.0898        | 2.5268 | 1000 | 0.1204          | 0.9585 |
+| 0.0904        | 2.7795 | 1100 | 0.1864          | 0.9294 |
+| 0.0936        | 3.0322 | 1200 | 0.1731          | 0.9543 |
+| 0.0644        | 3.2849 | 1300 | 0.1482          | 0.95   |
+| 0.0668        | 3.5376 | 1400 | 0.1713          | 0.9455 |
+| 0.0648        | 3.7903 | 1500 | 0.1499          | 0.9551 |
+| 0.0605        | 4.0430 | 1600 | 0.2150          | 0.9506 |
+| 0.0468        | 4.2956 | 1700 | 0.1913          | 0.9453 |
+| 0.0531        | 4.5483 | 1800 | 0.2022          | 0.9421 |
+| 0.0564        | 4.8010 | 1900 | 0.1694          | 0.9544 |
+| 0.0568        | 5.0537 | 2000 | 0.2193          | 0.9463 |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "Alibaba-NLP/gte-large-en-v1.5",
+  "architectures": [
+    "NewForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pack_qkv": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "rope",
+  "problem_type": "single_label_classification",
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "ntk"
+  },
+  "rope_theta": 160000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 30528
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd7094e1b9222b2b2ea048f3f3d2831c18e698edb1c363f5a75c5c3fe88bc52
+size 1740793696

runs/Dec06_06-42-58_d1c787833046/events.out.tfevents.1733467381.d1c787833046.533534.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20516c17ae745946ca1189530107b153cda613d45b17808cc348cf4920d3d018
+size 16864

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3504542a982a26ebf15ee9f79867c056600762ceaf1bcf1578028f189178c96
+size 5304